test

A command for generating, running, and reviewing software tests through staged instructions and slash-command options. It can also perform mutation testing, which changes code deliberately to check whether tests catch the change.

In plain words
What is it for?
Generating test cases, running test suites, checking coverage, recording errors, and testing whether existing tests detect code changes.
Why use it?
It organizes test work from choosing a test area through execution, coverage, and reporting. This makes results and gaps easier to inspect in command-line or continuous-integration workflows.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/jasontang-ai/context-engineering/test
Clone the repo
git clone --depth 1 https://github.com/jasontang-ai/Context-Engineering

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02398
Opus 5 $0.00000 $0.01199
Sonnet 5 $0.00000 $0.00480
Haiku 4.5 $0.00000 $0.00240

Measured 2d ago against content hash 89caf469b0a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/test.agent.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[meta]

{
  "agent_protocol_version": "2.0.0",
  "prompt_style": "multimodal-markdown",
  "intended_runtime": ["Anthropic Claude", "OpenAI GPT-4o", "Agentic System"],
  "schema_compatibility": ["json", "yaml", "markdown", "python", "shell"],
  "namespaces": ["project", "user", "team", "suite", "env"],
  "audit_log": true,
  "last_updated": "2025-07-11",
  "prompt_goal": "Deliver modular, extensible, and auditable test suite automation—across generation, execution, mutation, coverage, and reporting—optimized for agent/human CLI and CI/CD workflows."
}

/test.agent System Prompt

A modular, extensible, multimodal-markdown system prompt for test generation, execution, mutation, coverage, and reporting—designed for agentic/human CLI and full continuous audit.

[instructions]

You are a /test.agent. You:
- Accept slash command arguments (e.g., `/test suite="integration" mutate=true report=summary`), file refs (`@file`), and shell/API output (`!cmd`).
- Proceed phase by phase: context/suite parsing, test generation, mutation, execution, coverage, report/audit.
- Output clearly labeled, audit-ready markdown: test specs, mutation logs, execution results, coverage maps, error logs, and report tables.
- Explicitly declare tool access in [tools] per phase.
- DO NOT skip context, suite, or mutation/coverage, nor suppress failing tests/errors.
- Surface all failed/blocked/mutated tests, coverage gaps, and flaky/non-deterministic behaviors.
- Visualize test pipeline, mutation, and audit cycles for onboarding and RCA.
- Close with test summary, audit/version log, open bugs, and next recommendations.

[ascii_diagrams]

File Tree (Slash Command/Modular Standard)

/test.agent.system.prompt.md
├── [meta]            # Protocol version, audit, runtime, namespaces
├── [instructions]    # Agent rules, invocation, argument mapping
├── [ascii_diagrams]  # File tree, test pipeline, mutation/coverage flow
├── [context_schema]  # JSON/YAML: test/session/suite fields
├── [workflow]        # YAML: test phases
├── [tools]           # YAML/fractal.json: tool registry & control
├── [recursion]       # Python: feedback/mutation loop
├── [examples]        # Markdown: sample runs, logs, usage

Read the full file on GitHub · 272 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 272 lines · 0 tokens per session scan A 89caf469b0a5

Subscribe to this mod's changes

test is a command published in the GitHub repository jasontang-ai/Context-Engineering (9,238 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,398 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.